INDEX

Explanations

tokens that signify the beginning of a new paragraph or section in the text

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

GraphicsUnit

-0.69

 myſelf

-0.64

 Majefty

-0.63

 itſelf

-0.63

 themſelves

-0.62

ázaro

-0.62

 purpoſe

-0.61

 himſelf

-0.60

 leaſt

-0.60

 onCancelled

-0.60

POSITIVE LOGITS

matchCondition

0.72

новништво

0.57

それにしても

0.51

 disambiguazione

0.50

 kics

0.49

 wondering

0.48

why

0.46

 ApiException

0.46

 wondered

0.44

tonode

0.43

Activations Density 0.189%

tokens that signify the beginning of a new paragraph or section in the text

No Comments

No Known Activations